Triple
T12933399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermine Santruschitz |
E309439
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Paul Gies |
E311859
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Paul Gies | Statement: [Hermine Santruschitz, hasChild, Paul Gies]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Gies Context triple: [Hermine Santruschitz, hasChild, Paul Gies]
-
A.
Paul Gies
chosen
Paul Gies is the son of Miep Gies, the Dutch woman who helped hide Anne Frank and preserved her diary during World War II.
-
B.
Paul Graetz
Paul Graetz was a French film producer active in the mid-20th century, known for backing a range of notable European films.
-
C.
Walter Meierjohann
Walter Meierjohann is a theatre director known for his innovative, visually driven productions and leadership roles in European and UK theatre institutions.
-
D.
Walter Blum
Walter Blum is a German mathematician known for his contributions to algebra and mathematical education.
-
E.
Paul Kohner
Paul Kohner was a prominent Hollywood talent agent and film producer who represented major European and American stars during the mid-20th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97dc6517481908637781da240b51f |
completed | April 10, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d5f1023881909cbfe46a89b3e184 |
completed | May 3, 2026, 4:58 a.m. |
Created at: April 9, 2026, 5:42 p.m.